Loading…

Improved You Only Look Once v.8 Model Based on Deep Learning: Precision Detection and Recognition of Fresh Leaves from Yunnan Large-Leaf Tea Tree

Yunnan Province, China, known for its superior ecological environment and diverse climate conditions, is home to a rich resource of tea-plant varieties. However, the subtle differences in shape, color and size among the fresh leaves of different tea-plant varieties pose significant challenges for th...

Full description

Saved in:
Bibliographic Details
Published in:Agriculture (Basel) 2024-12, Vol.14 (12), p.2324
Main Authors: Wang, Chun, Li, Hongxu, Deng, Xiujuan, Liu, Ying, Wu, Tianyu, Liu, Weihao, Xiao, Rui, Wang, Zuzhen, Wang, Baijuan
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c1775-d08ff11d3bca3ce0c0fe7b149c3e08234b25ff4158bf692390632c9948da5283
container_end_page
container_issue 12
container_start_page 2324
container_title Agriculture (Basel)
container_volume 14
creator Wang, Chun
Li, Hongxu
Deng, Xiujuan
Liu, Ying
Wu, Tianyu
Liu, Weihao
Xiao, Rui
Wang, Zuzhen
Wang, Baijuan
description Yunnan Province, China, known for its superior ecological environment and diverse climate conditions, is home to a rich resource of tea-plant varieties. However, the subtle differences in shape, color and size among the fresh leaves of different tea-plant varieties pose significant challenges for their identification and detection. This study proposes an improved YOLOv8 model based on a dataset of fresh leaves from five tea-plant varieties among Yunnan large-leaf tea trees. Dynamic Upsampling replaces the UpSample module in the original YOLOv8, reducing the data volume in the training process. The Efficient Pyramid Squeeze Attention Network is integrated into the backbone of the YOLOv8 network to boost the network’s capability to handle multi-scale spatial information. To improve model performance and reduce the number of redundant features within the network, a Spatial and Channel Reconstruction Convolution module is introduced. Lastly, Inner-SIoU is adopted to reduce network loss and accelerate the convergence of regression. Experimental results indicate that the improved YOLOv8 model achieves precision, recall and an mAP of 88.4%, 89.9% and 94.8%, representing improvements of 7.1%, 3.9% and 3.4% over the original model. This study’s proposed improved YOLOv8 model not only identifies fresh leaves from different tea-plant varieties but also achieves graded recognition, effectively addressing the issues of strong subjectivity in manual identification detection, the long training time of the traditional deep learning model and high hardware cost. It establishes a robust technical foundation for the intelligent and refined harvesting of tea in Yunnan’s tea gardens.
doi_str_mv 10.3390/agriculture14122324
format article
fullrecord <record><control><sourceid>gale_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_8159de344a064b0bb688c5c3a540f68a</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A821602175</galeid><doaj_id>oai_doaj_org_article_8159de344a064b0bb688c5c3a540f68a</doaj_id><sourcerecordid>A821602175</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1775-d08ff11d3bca3ce0c0fe7b149c3e08234b25ff4158bf692390632c9948da5283</originalsourceid><addsrcrecordid>eNptUU1v1DAQjRBIVKW_gIslzln8lcThVgqlKwW1QnvpyZo44-Alay92slJ_Bv-43l2EONQ--HnmvaenmaJ4z-hKiJZ-hDE6s0zzEpFJxrng8lVxwWnTlFQ2_PV_-G1xldKW5tMyoWh9UfxZ7_YxHHAgj2Eh9356Il0IvzIySA4rRb6HASfyGVKmBE--IO5JhxC98-Mn8hDRuOROjRnNfETgB_IDTRi9O_2DJbcR08-j7ICJ2Bh25HHxHjzpII5Y5oYlGwSyiYjvijcWpoRXf9_LYnP7dXNzV3b339Y3111pWNNU5UCVtYwNojcgDFJDLTY9k60RSBUXsueVtZJVqrd1y_OgasFN20o1QMWVuCzWZ9shwFbvo9tBfNIBnD4VQhw1xNmZCbViVTugkBJoLXva97VSpjICKkltrSB7fTh75VH-XjDNehuW6HN6LXIi2daUVpm1OrNGyKbO2zBHMPkOuHMmeLQu168VZzXlrDkKxFlgYkgpov0Xk1F9XL1-YfXiGQIjovg</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3149496005</pqid></control><display><type>article</type><title>Improved You Only Look Once v.8 Model Based on Deep Learning: Precision Detection and Recognition of Fresh Leaves from Yunnan Large-Leaf Tea Tree</title><source>Publicly Available Content Database</source><creator>Wang, Chun ; Li, Hongxu ; Deng, Xiujuan ; Liu, Ying ; Wu, Tianyu ; Liu, Weihao ; Xiao, Rui ; Wang, Zuzhen ; Wang, Baijuan</creator><creatorcontrib>Wang, Chun ; Li, Hongxu ; Deng, Xiujuan ; Liu, Ying ; Wu, Tianyu ; Liu, Weihao ; Xiao, Rui ; Wang, Zuzhen ; Wang, Baijuan</creatorcontrib><description>Yunnan Province, China, known for its superior ecological environment and diverse climate conditions, is home to a rich resource of tea-plant varieties. However, the subtle differences in shape, color and size among the fresh leaves of different tea-plant varieties pose significant challenges for their identification and detection. This study proposes an improved YOLOv8 model based on a dataset of fresh leaves from five tea-plant varieties among Yunnan large-leaf tea trees. Dynamic Upsampling replaces the UpSample module in the original YOLOv8, reducing the data volume in the training process. The Efficient Pyramid Squeeze Attention Network is integrated into the backbone of the YOLOv8 network to boost the network’s capability to handle multi-scale spatial information. To improve model performance and reduce the number of redundant features within the network, a Spatial and Channel Reconstruction Convolution module is introduced. Lastly, Inner-SIoU is adopted to reduce network loss and accelerate the convergence of regression. Experimental results indicate that the improved YOLOv8 model achieves precision, recall and an mAP of 88.4%, 89.9% and 94.8%, representing improvements of 7.1%, 3.9% and 3.4% over the original model. This study’s proposed improved YOLOv8 model not only identifies fresh leaves from different tea-plant varieties but also achieves graded recognition, effectively addressing the issues of strong subjectivity in manual identification detection, the long training time of the traditional deep learning model and high hardware cost. It establishes a robust technical foundation for the intelligent and refined harvesting of tea in Yunnan’s tea gardens.</description><identifier>ISSN: 2077-0472</identifier><identifier>EISSN: 2077-0472</identifier><identifier>DOI: 10.3390/agriculture14122324</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Accuracy ; Climatic conditions ; Color ; Datasets ; Deep learning ; dynamic upsampling ; fresh tea leaves ; Identification ; improved YOLOv8 ; Information management ; Inner-SIoU ; Leaves ; Methods ; Modules ; Molecular biology ; Plants ; Regression models ; Spatial data ; Tea ; Training ; varieties of tea plants ; variety identification ; Wavelet transforms</subject><ispartof>Agriculture (Basel), 2024-12, Vol.14 (12), p.2324</ispartof><rights>COPYRIGHT 2024 MDPI AG</rights><rights>2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c1775-d08ff11d3bca3ce0c0fe7b149c3e08234b25ff4158bf692390632c9948da5283</cites><orcidid>0009-0009-2102-411X ; 0009-0004-4744-2719</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/3149496005/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/3149496005?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,25752,27923,27924,37011,44589,74997</link.rule.ids></links><search><creatorcontrib>Wang, Chun</creatorcontrib><creatorcontrib>Li, Hongxu</creatorcontrib><creatorcontrib>Deng, Xiujuan</creatorcontrib><creatorcontrib>Liu, Ying</creatorcontrib><creatorcontrib>Wu, Tianyu</creatorcontrib><creatorcontrib>Liu, Weihao</creatorcontrib><creatorcontrib>Xiao, Rui</creatorcontrib><creatorcontrib>Wang, Zuzhen</creatorcontrib><creatorcontrib>Wang, Baijuan</creatorcontrib><title>Improved You Only Look Once v.8 Model Based on Deep Learning: Precision Detection and Recognition of Fresh Leaves from Yunnan Large-Leaf Tea Tree</title><title>Agriculture (Basel)</title><description>Yunnan Province, China, known for its superior ecological environment and diverse climate conditions, is home to a rich resource of tea-plant varieties. However, the subtle differences in shape, color and size among the fresh leaves of different tea-plant varieties pose significant challenges for their identification and detection. This study proposes an improved YOLOv8 model based on a dataset of fresh leaves from five tea-plant varieties among Yunnan large-leaf tea trees. Dynamic Upsampling replaces the UpSample module in the original YOLOv8, reducing the data volume in the training process. The Efficient Pyramid Squeeze Attention Network is integrated into the backbone of the YOLOv8 network to boost the network’s capability to handle multi-scale spatial information. To improve model performance and reduce the number of redundant features within the network, a Spatial and Channel Reconstruction Convolution module is introduced. Lastly, Inner-SIoU is adopted to reduce network loss and accelerate the convergence of regression. Experimental results indicate that the improved YOLOv8 model achieves precision, recall and an mAP of 88.4%, 89.9% and 94.8%, representing improvements of 7.1%, 3.9% and 3.4% over the original model. This study’s proposed improved YOLOv8 model not only identifies fresh leaves from different tea-plant varieties but also achieves graded recognition, effectively addressing the issues of strong subjectivity in manual identification detection, the long training time of the traditional deep learning model and high hardware cost. It establishes a robust technical foundation for the intelligent and refined harvesting of tea in Yunnan’s tea gardens.</description><subject>Accuracy</subject><subject>Climatic conditions</subject><subject>Color</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>dynamic upsampling</subject><subject>fresh tea leaves</subject><subject>Identification</subject><subject>improved YOLOv8</subject><subject>Information management</subject><subject>Inner-SIoU</subject><subject>Leaves</subject><subject>Methods</subject><subject>Modules</subject><subject>Molecular biology</subject><subject>Plants</subject><subject>Regression models</subject><subject>Spatial data</subject><subject>Tea</subject><subject>Training</subject><subject>varieties of tea plants</subject><subject>variety identification</subject><subject>Wavelet transforms</subject><issn>2077-0472</issn><issn>2077-0472</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><sourceid>DOA</sourceid><recordid>eNptUU1v1DAQjRBIVKW_gIslzln8lcThVgqlKwW1QnvpyZo44-Alay92slJ_Bv-43l2EONQ--HnmvaenmaJ4z-hKiJZ-hDE6s0zzEpFJxrng8lVxwWnTlFQ2_PV_-G1xldKW5tMyoWh9UfxZ7_YxHHAgj2Eh9356Il0IvzIySA4rRb6HASfyGVKmBE--IO5JhxC98-Mn8hDRuOROjRnNfETgB_IDTRi9O_2DJbcR08-j7ICJ2Bh25HHxHjzpII5Y5oYlGwSyiYjvijcWpoRXf9_LYnP7dXNzV3b339Y3111pWNNU5UCVtYwNojcgDFJDLTY9k60RSBUXsueVtZJVqrd1y_OgasFN20o1QMWVuCzWZ9shwFbvo9tBfNIBnD4VQhw1xNmZCbViVTugkBJoLXva97VSpjICKkltrSB7fTh75VH-XjDNehuW6HN6LXIi2daUVpm1OrNGyKbO2zBHMPkOuHMmeLQu168VZzXlrDkKxFlgYkgpov0Xk1F9XL1-YfXiGQIjovg</recordid><startdate>20241201</startdate><enddate>20241201</enddate><creator>Wang, Chun</creator><creator>Li, Hongxu</creator><creator>Deng, Xiujuan</creator><creator>Liu, Ying</creator><creator>Wu, Tianyu</creator><creator>Liu, Weihao</creator><creator>Xiao, Rui</creator><creator>Wang, Zuzhen</creator><creator>Wang, Baijuan</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7SS</scope><scope>7ST</scope><scope>7T7</scope><scope>7X2</scope><scope>8FD</scope><scope>8FE</scope><scope>8FH</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AEUYN</scope><scope>AFKRA</scope><scope>ATCPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BHPHI</scope><scope>C1K</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FR3</scope><scope>HCIFZ</scope><scope>M0K</scope><scope>P64</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>SOI</scope><scope>DOA</scope><orcidid>https://orcid.org/0009-0009-2102-411X</orcidid><orcidid>https://orcid.org/0009-0004-4744-2719</orcidid></search><sort><creationdate>20241201</creationdate><title>Improved You Only Look Once v.8 Model Based on Deep Learning: Precision Detection and Recognition of Fresh Leaves from Yunnan Large-Leaf Tea Tree</title><author>Wang, Chun ; Li, Hongxu ; Deng, Xiujuan ; Liu, Ying ; Wu, Tianyu ; Liu, Weihao ; Xiao, Rui ; Wang, Zuzhen ; Wang, Baijuan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1775-d08ff11d3bca3ce0c0fe7b149c3e08234b25ff4158bf692390632c9948da5283</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Climatic conditions</topic><topic>Color</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>dynamic upsampling</topic><topic>fresh tea leaves</topic><topic>Identification</topic><topic>improved YOLOv8</topic><topic>Information management</topic><topic>Inner-SIoU</topic><topic>Leaves</topic><topic>Methods</topic><topic>Modules</topic><topic>Molecular biology</topic><topic>Plants</topic><topic>Regression models</topic><topic>Spatial data</topic><topic>Tea</topic><topic>Training</topic><topic>varieties of tea plants</topic><topic>variety identification</topic><topic>Wavelet transforms</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wang, Chun</creatorcontrib><creatorcontrib>Li, Hongxu</creatorcontrib><creatorcontrib>Deng, Xiujuan</creatorcontrib><creatorcontrib>Liu, Ying</creatorcontrib><creatorcontrib>Wu, Tianyu</creatorcontrib><creatorcontrib>Liu, Weihao</creatorcontrib><creatorcontrib>Xiao, Rui</creatorcontrib><creatorcontrib>Wang, Zuzhen</creatorcontrib><creatorcontrib>Wang, Baijuan</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Entomology Abstracts (Full archive)</collection><collection>Environment Abstracts</collection><collection>Industrial and Applied Microbiology Abstracts (Microbiology A)</collection><collection>Agricultural Science Collection</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest One Sustainability</collection><collection>ProQuest Central</collection><collection>Agricultural &amp; Environmental Science Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest Natural Science Collection</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>Engineering Research Database</collection><collection>SciTech Premium Collection</collection><collection>Agriculture Science Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Environment Abstracts</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Agriculture (Basel)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Chun</au><au>Li, Hongxu</au><au>Deng, Xiujuan</au><au>Liu, Ying</au><au>Wu, Tianyu</au><au>Liu, Weihao</au><au>Xiao, Rui</au><au>Wang, Zuzhen</au><au>Wang, Baijuan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Improved You Only Look Once v.8 Model Based on Deep Learning: Precision Detection and Recognition of Fresh Leaves from Yunnan Large-Leaf Tea Tree</atitle><jtitle>Agriculture (Basel)</jtitle><date>2024-12-01</date><risdate>2024</risdate><volume>14</volume><issue>12</issue><spage>2324</spage><pages>2324-</pages><issn>2077-0472</issn><eissn>2077-0472</eissn><abstract>Yunnan Province, China, known for its superior ecological environment and diverse climate conditions, is home to a rich resource of tea-plant varieties. However, the subtle differences in shape, color and size among the fresh leaves of different tea-plant varieties pose significant challenges for their identification and detection. This study proposes an improved YOLOv8 model based on a dataset of fresh leaves from five tea-plant varieties among Yunnan large-leaf tea trees. Dynamic Upsampling replaces the UpSample module in the original YOLOv8, reducing the data volume in the training process. The Efficient Pyramid Squeeze Attention Network is integrated into the backbone of the YOLOv8 network to boost the network’s capability to handle multi-scale spatial information. To improve model performance and reduce the number of redundant features within the network, a Spatial and Channel Reconstruction Convolution module is introduced. Lastly, Inner-SIoU is adopted to reduce network loss and accelerate the convergence of regression. Experimental results indicate that the improved YOLOv8 model achieves precision, recall and an mAP of 88.4%, 89.9% and 94.8%, representing improvements of 7.1%, 3.9% and 3.4% over the original model. This study’s proposed improved YOLOv8 model not only identifies fresh leaves from different tea-plant varieties but also achieves graded recognition, effectively addressing the issues of strong subjectivity in manual identification detection, the long training time of the traditional deep learning model and high hardware cost. It establishes a robust technical foundation for the intelligent and refined harvesting of tea in Yunnan’s tea gardens.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/agriculture14122324</doi><orcidid>https://orcid.org/0009-0009-2102-411X</orcidid><orcidid>https://orcid.org/0009-0004-4744-2719</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2077-0472
ispartof Agriculture (Basel), 2024-12, Vol.14 (12), p.2324
issn 2077-0472
2077-0472
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_8159de344a064b0bb688c5c3a540f68a
source Publicly Available Content Database
subjects Accuracy
Climatic conditions
Color
Datasets
Deep learning
dynamic upsampling
fresh tea leaves
Identification
improved YOLOv8
Information management
Inner-SIoU
Leaves
Methods
Modules
Molecular biology
Plants
Regression models
Spatial data
Tea
Training
varieties of tea plants
variety identification
Wavelet transforms
title Improved You Only Look Once v.8 Model Based on Deep Learning: Precision Detection and Recognition of Fresh Leaves from Yunnan Large-Leaf Tea Tree
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T02%3A51%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Improved%20You%20Only%20Look%20Once%20v.8%20Model%20Based%20on%20Deep%20Learning:%20Precision%20Detection%20and%20Recognition%20of%20Fresh%20Leaves%20from%20Yunnan%20Large-Leaf%20Tea%20Tree&rft.jtitle=Agriculture%20(Basel)&rft.au=Wang,%20Chun&rft.date=2024-12-01&rft.volume=14&rft.issue=12&rft.spage=2324&rft.pages=2324-&rft.issn=2077-0472&rft.eissn=2077-0472&rft_id=info:doi/10.3390/agriculture14122324&rft_dat=%3Cgale_doaj_%3EA821602175%3C/gale_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c1775-d08ff11d3bca3ce0c0fe7b149c3e08234b25ff4158bf692390632c9948da5283%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3149496005&rft_id=info:pmid/&rft_galeid=A821602175&rfr_iscdi=true